public void reduce(Text key, Iterable<IntWritable> values, Context context)
throws IOException, InterruptedException {
int sum = 0;
boolean filtered = true;
String keypair = key.toString();
String[] keys = keypair.split(" ");
if (keys.length == 1) {
filtered = false;
} else {
if (keys[0].equals("*") || keys[1].equals("*")) {
filtered = false;
}
}
if (!filtered) {
for (IntWritable val : values) {
sum += val.get();
}
context.write(key, new IntWritable(sum));
return;
}
for (IntWritable val : values) {
if (val.get() == -1) {
filtered = false;
continue;
}
sum += val.get();
}
// filter non-needed events
if (filtered) return;
context.write(key, new IntWritable(sum));
}
public void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
String file = value.toString();
String[] lines = file.split("\n");
for (String line : lines) {
if (line.contains("<author>") && line.contains("</author>")) {
String author = line.substring(8, line.indexOf("</a"));
word.set(author);
context.write(word, one);
} else if (line.contains("<author>")) {
String author = line.substring(8);
word.set(author);
context.write(word, one);
}
}
}
public void reduce(Text key, Iterable<IntWritable> values, Context context)
throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
context.write(key, new IntWritable(sum));
}
public void reduce(Text key, Iterable<LongWritable> values, Context context)
throws IOException, InterruptedException {
int sum = 0;
for (LongWritable val : values) {
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
context.write(word, one);
}
}
@Override
public void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
int movieId = Integer.parseInt(tokenizer.nextToken());
while (tokenizer.hasMoreTokens()) {
String word = tokenizer.nextToken();
context.write(new Text("1"), new IntWritable(1));
}
}
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
splitposition = line.indexOf("\t");
labels = line.substring(0, splitposition);
content = line.substring(splitposition + 1, line.length());
if (content.length() <= 5) {
word.set(labels);
int counter = Integer.parseInt(content);
context.write(word, new IntWritable(counter));
return;
}
labeltokens = labels.split(",");
contenttokens = tokenizeDoc(content);
for (String label : labelspace) {
for (String token : contenttokens) {
// filter token, denotes the needed events;
word.set(label + " " + token);
context.write(word, new IntWritable(-1));
}
}
}
public void reduce(Text key, Iterable<IntWritable> values, Context context)
throws IOException, InterruptedException {
context.write(key, new IntWritable(0));
}
